Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Suggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works31 from public data
- Pro-Cap: Leveraging a Frozen Vision-Language Model for Hateful Meme Detection115
This work proposes a probing-based captioning approach to leverage pre-trained vision-language models in a zero-shot visual question answering (VQA) manner and prompts a frozen PVLM by asking hateful content-related questions and uses the answers as image captions (which it calls Pro-Cap), so that the captions contain information critical for hateful content detection.
- Prompting Large Language Models for Topic Modeling72
This paper proposes PromptTopic, a novel topic modeling approach that harnesses the advanced language understanding of large language models (LLMs) to address challenges of short text datasets that lack co-occurring words.
- On Explaining Multimodal Hateful Meme Detection Models66
It is found that the image modality contributes more to the hateful meme classification task, and the visual-linguistic models are able to perform visual-text slurs grounding to a certain extent.
- LongGenBench: Benchmarking Long-Form Generation in Long Context LLMs62
It is revealed that, despite strong results on Ruler, all models struggled with long text generation on LongGenBench, particularly as text length increased, suggesting that current LLMs are not yet equipped to meet the demands of real-world, long-form text generation.
- Recent Advances in Online Hate Speech Moderation: Multimodality and the Role of Large Models58
This comprehensive survey delves into the recent strides in HS moderation, spotlighting the burgeoning role of large language models (LLMs) and large multimodal models (LMMs) and the development of more nuanced, context-aware systems.
- 31
- 30
- 24
- PromptMTopic: Unsupervised Multimodal Topic Modeling of Memes using Large Language Models24
This work proposes PromptMTopic, a novel multimodal prompt-based model designed to learn topics from both text and visual modalities by leveraging the language modeling capabilities of large language models, and demonstrates its superiority over state-of-the-art topic modeling baselines in learning descriptive topics in memes.
- Shifting Long-Context LLMs Research from Input to Output19
This paper advocates for a paradigm shift in NLP research toward addressing the challenges of long-output generation and calls for focused efforts to develop foundational LLMs tailored for generating high-quality, long-form outputs, which hold immense potential for real-world applications.
- TotalDefMeme: A Multi-Attribute Meme dataset on Total Defence in Singapore19
Besides supporting social informatics and public policy analysis of the Total Defence policy, TotalDefMeme can also support many downstream multi-modal machine learning tasks, such as aspect-based stance classification and multi- modal meme clustering.
- 14
- Recent Advances in Hate Speech Moderation: Multimodality and the Role of Large Models12
This comprehensive survey delves into the recent strides in HS moderation, spotlighting the burgeoning role of large language models (LLMs) and large multimodal models (LMMs) and uncover a notable trend towards integrating these modalities.
- 11
- Contrastive Instruction Fine-Tuning Large Multimodal Model for Hateful Meme Classification9
This study introduces a unique contrastive instruction fine-tuning approach, InstructMemeCL, that improves an LMM's ability to discern between memes that have similar visual or textual elements by intensifying its focus on semantic subtleties that separate hateful from non-hateful content.
- Understanding (Dark) Humour with Internet Meme Analysis8
This tutorial delivers an integrated framework for dissecting the complex humor of memes, weaving together disciplines such as natural language processing, computer vision, and multimodal modeling, empowering participants to decode meanings, analyze sentiments, and identify offensive content within memes.
- AISG's Online Safety Prize Challenge: Detecting Harmful Social Bias in Multimodal Memes7
The Online Safety Prize Challenge was held over ten weeks, focusing on the zero-shot detection of multilingual memes with harmful social bias within the Singaporean context, and an overview of the systems proposed across various languages and social biases were presented.
- 7
- 5
- Brinjal: A Web-Plugin for Collaborative Hate Speech Detection4
Brinjal is introduced, a multifaceted web plugin designed for the collaborative detection of hate speech that enables individuals to identify instances of HS and engage in discussions to verify such content, thereby enhancing the collective understanding of HS.
- Sword and Shield: Uses and Strategies of LLMs in Navigating Disinformation3
This paper investigates the complex dynamics between LLMs and disinformation in small, localised settings through a communication game based on online forums, inspired by Werewolf, with 25 participants, revealing both the potential for misuse and combating disinformation.
- Contrastive Disentanglement for Authorship Attribution3
This paper introduces ContrastDistAA, a novel framework that leverages contrastive learning and mutual information maximization to disentangle content and stylistic features in latent representations for AA, and surpasses existing state-of-the-art models in both individual and regional-level AA tasks.
- MATK: The Meme Analytical Tool Kit3
The Meme Analytical Tool Kit (MATK) is introduced, an open-source toolkit specifically designed to support existing memes datasets and cutting-edge multimodal models and provide analysis techniques to gain insights into their strengths and weaknesses.
- Linky: Visualizing User Identity Linkage Results for Multiple Online Social Networks3
Linky is a visual analytical tool which extracts the results from different user identity linkage methods performed on multiple online social networks and visualizes the user profiles, content and ego networks of the linked user identities.
- 2
- TABVERSE: Benchmarking Cross-Format Table Understanding in LLMs and VLMs1
TABVERSE is introduced, a controlled multimodal table benchmark that aligns the same table content across multiple structural formats and rendered images, with question category and difficulty tags, and shows that representation choice substantially affects table understanding.
- 1
- Usefulness and Diminishing Returns: Evaluating Social Information in Recommender Systems1
This paper introduces evaluation metrics to estimate the utilization of social information in the existing social recommendation models, and shows that there are diminishing returns when applying social information in recommender systems.
- Large Scale Narrative Analysis of Multimodal Memes–
This work introduces MemeTopicTrees (MemeTT), a zero-shot pipeline that clusters multimodal memes based on their targets, aspects, sentiments, and opinions and automates both semantic analysis and narrative generation at scale.
- –
- FRaN-X: FRaming and Narratives-eXplorer–
FRaN-X comprises a two-stage system that combines sequence labeling with fine-grained role classification to reveal how entities are portrayed as protagonists, antagonists, or innocents, using a unique taxonomy of 22 fine-grained roles nested under these three main categories.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-11. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.